Radiomics Analysis of Contrast-Enhanced Breast MRI for Optimized Modelling of Virtual Prognostic Biomarkers in Breast Cancer.

Objective: Breast cancer clinical stage and nodal status are the most clinically significant drivers of patient management, in combination with other pathological biomarkers, such as estrogen receptor (ER), progesterone receptor or human epidermal growth factor receptor 2 (HER2) receptor status and tumor grade. Accurate prediction of such parameters can help avoid unnecessary intervention, including unnecessary surgery. The objective was to investigate the role of magnetic resonance imaging (MRI) radiomics for yielding virtual prognostic biomarkers (ER, HER2 expression, tumor grade, molecular subtype, and T-stage). Materials and Methods: Patients with primary invasive breast cancer who underwent dynamic contrast-enhanced (DCE) breast MRI between July 2013 and July 2016 in a single center were retrospectively reviewed. Age, N-stage, grade, ER and HER2 status, and Ki-67 (%) were recorded. DCE images were segmented and Haralick texture features were extracted. The Bootstrap Lasso feature selection method was used to select a small subset of optimal texture features. Classification of the performance of the final model was assessed with the area under the receiver operating characteristic curve (AUC). Results: Median age of patients (n = 209) was 49 (21-79) years. Sensitivity, specificity, positive predictive value, negative predictive value and accuracy of the model for differentiating N0 vs N1-N3 was: 71%, 79%, 76%, 74%, 75% [AUC = 0.78 (95% confidence interval (CI) 0.72-0.85)], N0-N1 vs N2-N3 was 81%, 59%, 24%, 95%, 62% [AUC = 0.74 (95% CI 0.63-0.85)], distinguishing HER2(+) from HER2(-) was 79%, 48%, 34%, 87%, 56% [AUC = 0.64 (95% CI 0.54-0.73)], high nuclear grade (grade 2-3) vs low grade (grades 1) was 56%, 88%, 96%, 29%, 61% [AUC = 0.71 (95% CI 0.63-0.80)]; and for ER (+) vs ER(-) status the [AUC=0.67 (95% CI 0.59-0.76)]. Radiomics performance in distinguishing triple-negative vs other molecular subtypes was [0.60 (95% CI 0.49-0.71)], and Luminal A [0.66 (95% CI 0.56-0.76)]. Conclusion: Quantitative radiomics using MRI contrast texture shows promise in identifying aggressive high grade, node positive triple negative breast cancer, and correlated well with higher nuclear grades, higher T-stages, and N-positive stages.

Understanding and Mitigating Bias in Imaging Artificial Intelligence.

Artificial intelligence (AI) algorithms are prone to bias at multiple stages of model development, with potential for exacerbating health disparities. However, bias in imaging AI is a complex topic that encompasses multiple coexisting definitions. Bias may refer to unequal preference to a person or group owing to preexisting attitudes or beliefs, either intentional or unintentional. However, cognitive bias refers to systematic deviation from objective judgment due to reliance on heuristics, and statistical bias refers to differences between true and expected values, commonly manifesting as systematic error in model prediction (ie, a model with output unrepresentative of real-world conditions). Clinical decisions informed by biased models may lead to patient harm due to action on inaccurate AI results or exacerbate health inequities due to differing performance among patient populations. However, while inequitable bias can harm patients in this context, a mindful approach leveraging equitable bias can address underrepresentation of minority groups or rare diseases. Radiologists should also be aware of bias after AI deployment such as automation bias, or a tendency to agree with automated decisions despite contrary evidence. Understanding common sources of imaging AI bias and the consequences of using biased models can guide preventive measures to mitigate its impact. Accordingly, the authors focus on sources of bias at stages along the imaging machine learning life cycle, attempting to simplify potentially intimidating technical terminology for general radiologists using AI tools in practice or collaborating with data scientists and engineers for AI tool development. The authors review definitions of bias in AI, describe common sources of bias, and present recommendations to guide quality control measures to mitigate the impact of bias in imaging AI. Understanding the terms featured in this article will enable a proactive approach to identifying and mitigating bias in imaging AI. Published under a CC BY 4.0 license. Test Your Knowledge questions for this article are available in the supplemental material. See the invited commentary by Rouzrokh and Erickson in this issue.

Aromatase deficiency in transplanted bone marrow cells improves vertebral trabecular bone quantity, connectivity, and mineralization and decreases cortical porosity in murine bone marrow transplant recipients.

Estradiol is an important regulator of bone accumulation and maintenance. Circulating estrogens are primarily produced by the gonads. Aromatase, the enzyme responsible for the conversion of androgens to estrogen, is expressed by bone marrow cells (BMCs) of both hematopoietic and nonhematopoietic origin. While the significance of gonad-derived estradiol to bone health has been investigated, there is limited understanding regarding the relative contribution of BMC derived estrogens to bone metabolism. To elucidate the role of BMC derived estrogens in male bone, irradiated wild-type C57BL/6J mice received bone marrow cells transplanted from either WT (WT(WT)) or aromatase-deficient (WT(ArKO)) mice. MicroCT was acquired on lumbar vertebra to assess bone quantity and quality. WT(ArKO) animals had greater trabecular bone volume (BV/TV p = 0.002), with a higher trabecular number (p = 0.008), connectivity density (p = 0.017), and bone mineral content (p = 0.004). In cortical bone, WT(ArKO) animals exhibited smaller cortical pores and lower cortical porosity (p = 0.02). Static histomorphometry revealed fewer osteoclasts per bone surface (Oc.S/BS%), osteoclasts on the erosion surface (ES(Oc+)/BS, p = 0.04) and low number of osteoclasts per bone perimeter (N.Oc/B.Pm, p = 0.01) in WT(ArKO). Osteoblast-associated parameters in WT(ArKO) were lower but not statistically different from WT(WT). Dynamic histomorphometry suggested similar bone formation indices' patterns with lower mean values in mineral apposition rate, label separation, and BFR/BS in WT(ArKO) animals. Ex vivo bone cell differentiation assays demonstrated relative decreased osteoblast differentiation and ability to form mineralized nodules. This study demonstrates a role of local 17ß-estradiol production by BMCs for regulating the quantity and quality of bone in male mice. Underlying in vivo cellular and molecular mechanisms require further study.

A Tale of Two Hospitals: Effect of Access to Care Through a Safety Net Hospital on Adjuvant Therapy, Imaging Compliance and 5-Year Survival Rates Compared to the University Hospital Served by the Same Breast Cancer Clinical Teams.

RATIONALE AND OBJECTIVES: To compare rates of guideline-concordant care, imaging surveillance, recurrence and survival outcomes between a safety-net (SNH) and tertiary-care University Hospital (UH) served by the same breast cancer clinical teams. MATERIALS AND METHODS: 647 women with newly diagnosed breast cancer treated in affiliated SNH and UH between 11.1.2014 and 3.31.2017 were reviewed. Patient demographics, completion of guideline-concordant adjuvant chemotherapy, radiation and hormonal therapy were recorded. Two multivariable logistic regression models were performed to investigate the effect of hospital and race on cancer stage. Kaplan-Meier log-rank and Cox-regression were used to analyze five-year recurrence-free (RFS) and overall survival (OS) between hospitals and races, (p < 0.05 significant). RESULTS: Patients in SNH were younger (mean SNH 53.2 vs UH 57.9, p < 0.001) and had higher rates of cT3/T4 disease (SNH 19% vs UH 5.5%, p < 0.001). Patients in the UH had higher rates of bilateral mastectomy (SNH 17.6% vs UH 40.1% p < 0.001) while there was no difference in the positive surgical margin rate (SNH 5.0% vs UH 7.6%, p = 0.20), completion of adjuvant radiation (SNH 96.9% vs UH 98.7%, p = 0.2) and endocrine therapy (SNH 60.8% vs UH 66.2%, p = 0.20). SNH patients were less compliant with mammography surveillance (SNH 64.1% vs UH 75.1%, p = 0.02) and adjuvant chemotherapy (SNH 79.1% vs UH 96.3%, p < 0.01). RFS was lower in the SNH (SNH 54 months vs UH 57 months, HR 1.90, 95% CI: 1.18-3.94, p = 0.01) while OS was not significantly different (SNH 90.5% vs UH 94.2%, HR 1.78, 95% CI: 0.97-3.26, p = 0.06). CONCLUSION: In patients experiencing health care disparities, having access to guideline-concordant care through SNH resulted in non-inferior OS to those in tertiary-care UH.

Magnetic resonance imaging improves diagnosis of placenta accreta spectrum requiring hysterectomy compared to ultrasound.

BACKGROUND: Magnetic resonance imaging has been used increasingly as an adjunct for ultrasound imaging for placenta accreta spectrum assessment and preoperative surgical planning, but its value has not been established yet. The ultrasound-based placenta accreta index is a well-validated standardized approach for placenta accreta spectrum evaluation. Placenta accreta spectrum-magnetic resonance imaging markers have been outlined in a joint guideline from the Society of Abdominal Radiology and the European Society of Urogenital Radiology. OBJECTIVE: This study aimed to compare placenta accreta spectrum-magnetic resonance imaging parameters with the ultrasound-based placenta accreta index in pregnancies at high risk for placenta accreta spectrum and to assess the additional diagnostic value of magnetic resonance imaging for placenta accreta spectrum that requires a cesarean hysterectomy. STUDY DESIGN: This was a single-center, retrospective study of pregnant patients who underwent magnetic resonance imaging, in addition to ultrasonography, because of suspected placenta accreta spectrum. The ultrasound-based placenta accreta index and placenta accreta spectrum-magnetic resonance imaging parameters were obtained. Student's t test and Fisher's exact test were used to compare the groups in terms of the primary outcome (hysterectomy vs no hysterectomy). The diagnostic performance of magnetic resonance imaging and the ultrasound-based placenta accreta index was assessed using multivariable logistic regressions, receiver operating characteristics curves, the DeLong test, McNemar test, and the relative predictive value test. RESULTS: A total of 82 patients were included in the study, 41 of whom required a hysterectomy. All patients who underwent a hysterectomy met the International Federation of Gynecology and Obstetrics clinical evidence of placenta accreta spectrum at the time of delivery. Multiple parameters of the ultrasound-based placenta accreta index and placenta accreta spectrum-magnetic resonance imaging were able to predict hysterectomy, and the parameter of greatest dimension of invasion by magnetic resonance imaging was the best quantitative predictor. At 96% sensitivity for hysterectomy, the cutoff values were 3.5 for the ultrasound-based placenta accreta index and 2.5 cm for the greatest dimension of invasion by magnetic resonance imaging. Using this sensitivity, the parameter of greatest dimension of invasion measured by magnetic resonance imaging had higher specificity (P=.0016) and a higher positive predictive value (P=.0018) than the ultrasound-based placenta accreta index, indicating an improved diagnostic threshold. CONCLUSION: In a suspected high-risk group for placenta accreta spectrum, magnetic resonance imaging identified more patients who will not need a hysterectomy than when using the ultrasound-based placenta accrete index only. Magnetic resonance imaging has the potential to aid patient counseling, surgical planning, and delivery timing, including preterm delivery decisions for patients with placenta accreta spectrum requiring hysterectomy.

Three-dimensional Volumetric Visceral and Subcutaneous Fat Analysis on Opportunistic Computed Tomography Imaging of Patients With Greater Trochanteric Pain Syndrome Compared With Those With Predominant Osteoarthritis: A Case-Control Study.

OBJECTIVE: This study aimed to address the gap in knowledge assessing the impact of visceral and subcutaneous body fat on 3-dimensional computed tomography imaging in patients with greater trochanteric pain syndrome (GTPS) in comparison with those primarily diagnosed with osteoarthritis (OA). MATERIALS AND METHODS: We evaluated adult patients with a confirmed diagnosis of GTPS from our institutional hip-preservation clinic spanning 2011 to 2022. Selection criteria included their initial clinic visit for hip pain and a concurrent pelvis computed tomography scan. These patients were age- and sex-matched to mild-moderate OA patients selected randomly from the database. Visceral and subcutaneous fat areas were measured volumetrically from the sacroiliac joint to the lesser trochanter using an independent software. Interreader reliability was also calculated. RESULTS: A total of 93 patients met the study criteria, of which 37 belonged to the GTPS group and 56 belonged to the OA group. Both groups were sex and race matched. Average age in GTPS and OA groups was 59.3 years and 56 years, respectively. For GTPS group, average body mass index was 28.9 kg/m2, and for the OA group, average body mass index was 29.9 kg/m2, with no significant difference (P > 0.05). Two-sample t test showed no significant differences in the visceral fat, subcutaneous fat, or the visceral fat to total fat volume ratio between the GTPS and OA groups. There was excellent interreader reliability. CONCLUSIONS: Our results indicate that there is no significant difference in fat distribution and volumes among GTPS and OA patients. This suggests that being overweight or obese may not be directly linked or contribute to the onset of GTPS. Other factors, such as gluteal tendinopathy, bursitis, or iliotibial band syndrome, might be responsible and need further investigation.

Characterization of Demographical Histologic Diversity in Small Renal Masses With the Clear Cell Likelihood Score.

OBJECTIVE: This study aimed to develop a diagnostic model to estimate the distribution of small renal mass (SRM; ≤4 cm) histologic subtypes for patients with different demographic backgrounds and clear cell likelihood score (ccLS) designations. MATERIALS AND METHODS: A bi-institution retrospective cohort study was conducted where 347 patients (366 SRMs) underwent magnetic resonance imaging and received a ccLS before pathologic confirmation between June 2016 and November 2021. Age, sex, race, ethnicity, socioeconomic status, body mass index (BMI), and the ccLS were tabulated. The socioeconomic status for each patient was determined using the Area Deprivation Index associated with their residential address. The magnetic resonance imaging-derived ccLS assists in the characterization of SRMs by providing a likelihood of clear cell renal cell carcinoma (ccRCC). Pathological subtypes were grouped into four categories (ccRCC, papillary renal cell carcinoma, other renal cell carcinomas, or benign). Generalized estimating equations were used to estimate probabilities of the pathological subtypes across different patient subgroups. RESULTS: Race and ethnicity, BMI, and ccLS were significant predictors of histology (all P < 0.001). Obese (BMI, ≥30 kg/m2) Hispanic patients with ccLS of ≥4 had the highest estimated rate of ccRCC (97.1%), and normal-weight (BMI, <25 kg/m2) non-Hispanic Black patients with ccLS ≤2 had the lowest (0.2%). The highest estimated rates of papillary renal cell carcinoma were found in overweight (BMI, 25-30 kg/m2) non-Hispanic Black patients with ccLS ≤2 (92.3%), and the lowest, in obese Hispanic patients with ccLS ≥4 (<0.1%). CONCLUSIONS: Patient race, ethnicity, BMI, and ccLS offer synergistic information to estimate the probabilities of SRM histologic subtypes.

MRI-based Neuropathy Score Reporting And Data System (NS-RADS): multi-institutional wider-experience usability study of peripheral neuropathy conditions among 32 radiology readers.

OBJECTIVE: To determine the inter-reader reliability and diagnostic performance of classification and severity scales of Neuropathy Score Reporting And Data System (NS-RADS) among readers of differing experience levels after limited teaching of the scoring system. METHODS: This is a multi-institutional, cross-sectional, retrospective study of MRI cases of proven peripheral neuropathy (PN) conditions. Thirty-two radiology readers with varying experience levels were recruited from different institutions. Each reader attended and received a structured presentation that described the NS-RADS classification system containing examples and reviewed published articles on this subject. The readers were then asked to perform NS-RADS scoring with recording of category, subcategory, and most likely diagnosis. Inter-reader agreements were evaluated by Conger's kappa and diagnostic accuracy was calculated for each reader as percent correct diagnosis. A linear mixed model was used to estimate and compare accuracy between trainees and attendings. RESULTS: Across all readers, agreement was good for NS-RADS category and moderate for subcategory. Inter-reader agreement of trainees was comparable to attendings (0.65 vs 0.65). Reader accuracy for attendings was 75% (95% CI 73%, 77%), slightly higher than for trainees (71% (69%, 72%), p = 0.0006) for nerves and comparable for muscles (attendings, 87.5% (95% CI 86.1-88.8%) and trainees, 86.6% (95% CI 85.2-87.9%), p = 0.4). NS-RADS accuracy was also higher than average accuracy for the most plausible diagnosis for attending radiologists at 67% (95% CI 63%, 71%) and for trainees at 65% (95% CI 60%, 69%) (p = 0.036). CONCLUSION: Non-expert radiologists interpreted PN conditions with good accuracy and moderate-to-good inter-reader reliability using the NS-RADS scoring system. CLINICAL RELEVANCE STATEMENT: The Neuropathy Score Reporting And Data System (NS-RADS) is an accurate and reliable MRI-based image scoring system for practical use for the diagnosis and grading of severity of peripheral neuromuscular disorders by both experienced and general radiologists. KEY POINTS: • The Neuropathy Score Reporting And Data System (NS-RADS) can be used effectively by non-expert radiologists to categorize peripheral neuropathy. • Across 32 different experience-level readers, the agreement was good for NS-RADS category and moderate for NS-RADS subcategory. • NS-RADS accuracy was higher than the average accuracy for the most plausible diagnosis for both attending radiologists and trainees (at 75%, 71% and 65%, 65%, respectively).

Deficiency of FRMD5 results in neurodevelopmental dysfunction and autistic-like behavior in mice.

The pathophysiology of autism spectrum disorders (ASDs) is causally linked to postsynaptic scaffolding proteins, as evidenced by numerous large-scale genomic studies [1, 2] and in vitro and in vivo neurobiological studies of mutations in animal models [3, 4]. However, due to the distinct phenotypic and genetic heterogeneity observed in ASD patients, individual mutation genes account for only a small proportion (<2%) of cases [1, 5]. Recently, a human genetic study revealed a correlation between de novo variants in FERM domain-containing-5 (FRMD5) and neurodevelopmental abnormalities [6]. In this study, we demonstrate that deficiency of the scaffolding protein FRMD5 leads to neurodevelopmental dysfunction and ASD-like behavior in mice. FRMD5 deficiency results in morphological abnormalities in neurons and synaptic dysfunction in mice. Frmd5-deficient mice display learning and memory dysfunction, impaired social function, and increased repetitive stereotyped behavior. Mechanistically, tandem mass tag (TMT)-labeled quantitative proteomics revealed that FRMD5 deletion affects the distribution of synaptic proteins involved in the pathological process of ASD. Collectively, our findings delineate the critical role of FRMD5 in neurodevelopment and ASD pathophysiology, suggesting potential therapeutic implications for the treatment of ASD.

Next Level of Care Protocols in Radiology: Improving Patient Access to Care.

OBJECTIVE: To introduce a novel next level of care (NLC) protocol used in our breast imaging practice to bypass additional imaging and image-guided biopsy orders and to examine the impact of NLC on breast biopsy wait times compared with thyroid biopsy wait times, which do not use NLC. METHODS: Our institutional review board deemed this retrospective analysis to be exempt. NLC was implemented for breast imaging in late 2014. Two 6-month periods before and after the COVID-19 shutdown were sampled and compiled. Data were queried from departmental database and electronic health record for all breast and thyroid biopsies during this time. Time to biopsy (TTB) was defined as the number of days from the diagnostic imaging evaluation recommending the biopsy to the completion of the biopsy. To determine the effect of NLC, TTB was compared between breast and thyroid biopsies. RESULTS: Of the 1,114 breast biopsies and 154 thyroid biopsies included, the mean TTB was 9 days (95% confidence interval 8.4-9.3) for breast and 23 days (95% confidence interval 20.5-25.0) for thyroid. There was a 61% reduction in the mean TTB for patients in the breast group compared with patients in the thyroid group. The effect of the NLC was comparable among different races and ethnicities in the breast group, but a significantly higher mean TTB (24% higher, P = .025) was observed for thyroid biopsies in Black patients compared with thyroid biopsies in Hispanic patients. CONCLUSION: NLC protocol facilitates imaging evaluations and reduces the time interval to image-guided biopsies.

Supplemental Optoacoustic Imaging of Breast Masses: A Cost-Effectiveness Analysis.

RATIONALE AND OBJECTIVES: To evaluate the cost-effectiveness of utilizing supplemental optoacoustic ultrasound (OA/US) versus gray-scale ultrasound (US) alone to differentiate benign and malignant breast masses in a diagnostic setting. MATERIALS AND METHODS: We created a decision-tree model to compare the cost-effectiveness of OA/US and US from the perspective of the US healthcare system. We utilized diagnostic test performance parameters from the PIONEER-01(NCT01943916) clinical trial and cost parameters (USD) from the Truven Health MarketScan Databases. Utility (quality adjusted life year, QALY) values were determined following published patient-reported outcomes. Cost-effectiveness was calculated through incremental cost-effectiveness ratio (USD/QALY, ICER) and net monetary benefit (NMB) in a Markov chain model. Deterministic and probabilistic sensitivity analyses were performed to determine the significance of variation in input parameters. A willingness-to-pay (WTP) threshold of $100,000/QALY was used for the study. RESULTS: OA/US had an estimated cumulative cost of $16,617.36 and the outcome of 16.85 QALYs in the 25-year period. The incremental NMB for OA/US was $1495.36, and the ICER was -$31,715.82/QALY, indicating that supplemental use of OA/US was more cost-effective than US alone. In the deterministic sensitivity analysis, when the cost of OA/US exceeded $1030.61 or the sensitivity of OA/US fell below 79.7%, or the specificity fell below 30.5%, the US alone strategy yielded higher NMB values compared to supplemental OA/US. According to probabilistic sensitivity analysis, OA/US was the better strategy in 98.69% of 10,000 iterations. CONCLUSION: OA/US is more cost-effective than US to differentiate benign or malignant breast masses in the diagnostic setting. It can reduce costs while improving patients' quality of life, primarily by reducing false-positive results with consequent benign biopsies.

Testicular Radiomics To Predict Pathology At Time of Postchemotherapy Retroperitoneal Lymph Node Dissection for Nonseminomatous Germ Cell Tumor.

INTRODUCTION: Testicular germ cell tumors are the most common malignancy in young adult males. Patients with metastatic disease receive standard of care chemotherapy followed by retroperitoneal lymph node dissection for residual masses >1cm. However, there is a need for better preoperative tools to discern which patients will have persistent disease after chemotherapy given low rates of metastatic germ cell tumor after chemotherapy. The purpose of this study was to use radiomics to predict which patients would have viable germ cell tumor or teratoma after chemotherapy at time of retroperitoneal lymph node dissection. PATIENTS AND METHODS: Patients with nonseminomatous germ cell tumor undergoing postchemotherapy retroperitoneal lymph node dissection (PC-RPLND) between 2008 and 2019 were queried from our institutional database. Patients were included if prechemotherapy computed tomography (CT) scan and postchemotherapy imaging were available. Semiqualitative and quantitative features of residual masses and nodal regions of interest and radiomic feature extractions were performed by 2 board certified radiologists. Radiomic feature analysis was used to extract first order, shape, and second order statistics from each region of interest. Post-RPLND pathology was compared to the radiomic analysis using multiple t-tests. RESULTS: 45 patients underwent PC-RPLND at our institution, with the majority (28 patients) having stage III disease. 24 (53%) patients had teratoma on RPLND pathology, while 2 (4%) had viable germ cell tumor. After chemotherapy, 78%, 53%, and 33% of patients had cystic regions, fat stranding, and local infiltration present on imaging. After radiomic analysis, first order statistics mean, median, 90th percentile, and root mean squares were significant. Strong correlations were observed between these 4 features;a lower signal was associated with positive pathology at RPND. CONCLUSIONS: Testicular radiomics is an emerging tool that may help predict persistent disease after chemotherapy.

Style Transfer-assisted Deep Learning Method for Kidney Segmentation at Multiphase MRI.

Purpose: To develop and validate a semisupervised style transfer-assisted deep learning method for automated segmentation of the kidneys using multiphase contrast-enhanced (MCE) MRI acquisitions. Materials and Methods: This retrospective, Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included 125 patients (mean age, 57.3 years; 67 male, 58 female) with renal masses. Cohort 1 consisted of 102 coronal T2-weighted MRI acquisitions and 27 MCE MRI acquisitions during the corticomedullary phase. Cohort 2 comprised 92 MCE MRI acquisitions (23 acquisitions during four phases each, including precontrast, corticomedullary, early nephrographic, and nephrographic phases). The kidneys were manually segmented on T2-weighted images. A cycle-consistent generative adversarial network (CycleGAN) was trained to generate anatomically coregistered synthetic corticomedullary style images using T2-weighted images as input. Synthetic images for precontrast, early nephrographic, and nephrographic phases were then generated using the synthetic corticomedullary images as input. Mask region-based convolutional neural networks were trained on the four synthetic phase series for kidney segmentation using T2-weighted masks. Segmentation performance was evaluated in a different cohort of 20 originally acquired MCE MRI examinations by using Dice and Jaccard scores. Results: The CycleGAN network successfully generated anatomically coregistered synthetic MCE MRI-like datasets from T2-weighted acquisitions. The proposed deep learning approach for kidney segmentation achieved high mean Dice scores in all four phases of the original MCE MRI acquisitions (0.91 for precontrast, 0.92 for corticomedullary, 0.91 for early nephrographic, and 0.93 for nephrographic). Conclusion: The proposed deep learning approach achieved high performance in kidney segmentation on different MCE MRI acquisitions.Keywords: Kidney Segmentation, Generative Adversarial Network, CycleGAN, Convolutional Neural Network, Transfer Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.

Venovenous extracorporeal membrane oxygenation for COVID-19 and influenza H1N1 associated acute respiratory distress syndrome: A comparative cohort study in China.

Background: Venovenous extracorporeal membrane oxygenation (VV-ECMO) has been demonstrated to be effective in treating patients with virus-induced acute respiratory distress syndrome (ARDS). However, whether the management of ECMO is different in treating H1N1 influenza and coronavirus disease 2019 (COVID-19)-associated ARDS patients remains unknown. Methods: This is a retrospective cohort study. We included 12 VV-ECMO-supported COVID-19 patients admitted to The First Affiliated Hospital of Guangzhou Medical University, Guangzhou Eighth People's Hospital, and Wuhan Union Hospital West Campus between January 23 and March 31, 2020. We retrospectively included VV-ECMO-supported patients with COVID-19 and H1N1 influenza-associated ARDS. Clinical characteristics, respiratory mechanics including plateau pressure, driving pressure, mechanical power, ventilatory ratio (VR) and lung compliance, and outcomes were compared. Results: Data from 25 patients with COVID-19 (n=12) and H1N1 (n=13) associated ARDS who had received ECMO support were analyzed. COVID-19 patients were older than H1N1 influenza patients (P=0.004). The partial pressure of arterial carbon dioxide (PaCO2) and VR before ECMO initiation were significantly higher in COVID-19 patients than in H1N1 influenza patients (P <0.001 and P=0.004, respectively). COVID-19 patients showed increased plateau and driving pressure compared with H1N1 subjects (P=0.013 and P=0.018, respectively). Patients with COVID-19 remained longer on ECMO support than did H1N1 influenza patients (P=0.015). COVID-19 patients who required ECMO support also had fewer intensive care unit and ventilator-free days than H1N1. Conclusions: Compared with H1N1 influenza patients, COVID-19 patients were older and presented with increased PaCO2 and VR values before ECMO initiation. The differences between ARDS patients with COVID-19 and influenza on VV-ECMO detailed herein could be helpful for obtaining a better understanding of COVID-19 and for better clinical management.

Single-Plane 3-Dimensional Isotropic Spin-Echo Magnetic Resonance Imaging Reconstructions of Shoulder Exhibit Superior Correlation to Surgical Findings Than 2-Dimensional Dixon Multiplanar Magnetic Resonance Imaging.

OBJECTIVE: The aim of the study is to evaluate concordance of multiplanar 2-dimensional magnetic resonance imaging (2D-MRI) versus 3D isotropic MRI for rotator cuff and labral tears with the reference standard of arthroscopic surgical findings. METHODS: It was an institutional review board-approved retrospective single-center study of consecutive preoperative patients with isotropic 3D-MRI on 3-Tesla scanners, multiplanar 2D-MRI, and shoulder arthroscopy. Scapular plane-oriented contiguous multiplanar reconstructions of 3D-images were evaluated by 2 experienced fellowship-trained musculoskeletal radiologists. Variables included the following: labral tear presence and rotator-cuff tear Ellman grade, thickness, and width. Sensitivities (Sen) and specificities (Spe) were calculated for binary variables. Mean squared errors (MSE) were calculated for ordinal variables. Lower MSE indicated higher concordance. RESULTS: Seventy-two patients (43 female) with a mean age of 50.75 ± 9.76 years were evaluated. For infraspinatus-tear presence, 3D-MRI showed higher sensitivity (0.96) and specificity (0.68) than 2D-MRI (Sen = 0.85, Spe = 0.32) (Psen = 0.005, Pspe = 0.002). For subscapularis-tear presence, 3D-MRI showed higher sensitivity (0.94) and specificity (0.73) compared with 2D-MRI (Sen = 0.83, Spe = 0.56) (Psen = 0.02, Pspe = 0.04). For supraspinatus-tear presence, there was no significant difference between 3D-MRI (Sen =0.96, Spe = 0.67) compared with 2D-MRI (Sen = 0.98, Spe = 0.83) (Psen = 0.43, Pspe = 0.63). For infraspinatus-tear thickness, 3D-MRI showed lower MSE (0.35) compared with 2D-MRI MSE (0.82) (P = 0.01). For subscapularis-tear thickness, 3D-MRI had lower MSE (0.31) compared with 2D-MRI MSE (0.51) (P = 0.007). However, no difference noted for supraspinatus-tear thickness when comparing 3D-MRI MSE (0.39) and 2D-MRI MSE (0.51) (P = 0.49). For labral-tear presence, 3D-MRI had a lower MSE (0.20) compared with 2D-MRI MSE (0.57) (P < 0.001). CONCLUSIONS: Three-dimensional MRI of the shoulder is time efficient with a shorter acquisition time and exhibits comparable with superior correlation to surgical findings than 2D-MRI for detection of labral tears and some rotator cuff tears. Three-dimensional MRI may be used in place of traditional 2D-MRI in detection of soft-tissue shoulder injury in centers equipped to do so.

Deep learning generated lower extremity radiographic measurements are adequate for quick assessment of knee angular alignment and leg length determination.

PURPOSE: Angular and longitudinal deformities of leg alignment create excessive stresses across joints, leading to pain and impaired function. Multiple measurements are used to assess these deformities on anteroposterior (AP) full-length radiographs. An artificial intelligence (AI) software automatically locates anatomical landmarks on AP full-length radiographs and performs 13 measurements to assess knee angular alignment and leg length. The primary aim of this study was to evaluate the agreements in LLD and knee alignment measurements between an AI software and two board-certified radiologists in patients without metal implants. The secondary aim was to assess time savings achieved by AI. METHODS: The measurements assessed in the study were hip-knee-angle (HKA), anatomical-tibiofemoral angle (aTFA), anatomical-mechanical-axis angle (AMA), joint-line-convergence angle (JLCA), mechanical-lateral-proximal-femur-angle (mLPFA), mechanical-lateral-distal-femur-angle (mLDFA), mechanical-medial-proximal-tibia-angle (mMPTA), mechanical-lateral-distal-tibia- angle (mLDTA), femur length, tibia length, full leg length, leg length discrepancy (LLD), and mechanical axis deviation (MAD). These measurements were performed by two radiologists and the AI software on 164 legs. Intraclass-correlation-coefficients (ICC) and Bland-Altman analyses were used to assess the AI's performance. RESULTS: The AI software set incorrect landmarks for 11/164 legs. Excluding these cases, ICCs between the software and radiologists were excellent for 12/13 variables (11/13 with outliers included), and the AI software met performance targets for 11/13 variables (9/13 with outliers included). The mean reading time for the AI algorithm and two readers, respectively, was 38.3, 435.0, and 625.0 s. CONCLUSION: This study demonstrated that, with few exceptions, this AI-based software reliably generated measurements for most variables in the study and provided substantial time savings.

Unveiling adcyap1 as a protective factor linking pain and nerve regeneration through single-cell RNA sequencing of rat dorsal root ganglion neurons.

BACKGROUND: Severe peripheral nerve injury (PNI) often leads to significant movement disorders and intractable pain. Therefore, promoting nerve regeneration while avoiding neuropathic pain is crucial for the clinical treatment of PNI patients. However, established animal models for peripheral neuropathy fail to accurately recapitulate the clinical features of PNI. Additionally, researchers usually investigate neuropathic pain and axonal regeneration separately, leaving the intrinsic relationship between the development of neuropathic pain and nerve regeneration after PNI unclear. To explore the underlying connections between pain and regeneration after PNI and provide potential molecular targets, we performed single-cell RNA sequencing and functional verification in an established rat model, allowing simultaneous study of the neuropathic pain and axonal regeneration after PNI. RESULTS: First, a novel rat model named spared nerve crush (SNC) was created. In this model, two branches of the sciatic nerve were crushed, but the epineurium remained unsevered. This model successfully recapitulated both neuropathic pain and axonal regeneration after PNI, allowing for the study of the intrinsic link between these two crucial biological processes. Dorsal root ganglions (DRGs) from SNC and naïve rats at various time points after SNC were collected for single-cell RNA sequencing (scRNA-seq). After matching all scRNA-seq data to the 7 known DRG types, we discovered that the PEP1 and PEP3 DRG neuron subtypes increased in crushed and uncrushed DRG separately after SNC. Using experimental design scRNA-seq processing (EDSSP), we identified Adcyap1 as a potential gene contributing to both pain and nerve regeneration. Indeed, repeated intrathecal administration of PACAP38 mitigated pain and facilitated axonal regeneration, while Adcyap1 siRNA or PACAP6-38, an antagonist of PAC1R (a receptor of PACAP38) led to both mechanical hyperalgesia and delayed DRG axon regeneration in SNC rats. Moreover, these effects can be reversed by repeated intrathecal administration of PACAP38 in the acute phase but not the late phase after PNI, resulting in alleviated pain and promoted axonal regeneration. CONCLUSIONS: Our study reveals that Adcyap1 is an intrinsic protective factor linking neuropathic pain and axonal regeneration following PNI. This finding provides new potential targets and strategies for early therapeutic intervention of PNI.